Abstract
This chapter is devoted to the 2-years development and exploitation of the repository platform built at Warsaw University of Technology for the purpose of gathering University research knowledge. The platform has been developed under the SYNAT project, aimed at building nation-wide scientific information infrastructure. The implementation of the platform in the form of the advanced information system is discussed. New functionalities of the knowledge base are presented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Involving researchers directly into the data acquisition process was presumed as a psychologically important factor for achieving the data completeness. Bearing in mind a possible drop down of data quality, unavoidable for such approach, a variety of new tools guarantying high level of acquisition process have been developed recently—they are mainly based on web mining and will be presented in Sect. 3.
- 2.
This information is planned for being applied when the acquisition process based on web mining is extended on searching for the involvement into conferences PC.
- 3.
For the internal needs, the module presents the tags in the form of a vector, and it visualizes it for the end-users as a word cloud. The word cloud can be “calculated” for the authors, and for the affiliations by aggregating cloud vectors assigned to the papers, supervised theses, run projects etc. This helps the user to pick the most probable area of expertise rather than test the casual phrases.
- 4.
This algorithm causes that publications where the keyword occurred frequently (for example in full text, extracted paper keywords, journal name, journal keyword) are scored higher, moreover the journal impact factor increases the ranking.
- 5.
The first level of OSJ is too general, it has six broad categories: Natural Sciences, Applied Sciences, Health Sciences, Economics and Social Sciences, Arts and Humanities and General, whereas the third level is too detailed, and there is a problem with finding out a training set with a uniform distribution of categories and representative number of examples per category.
- 6.
They are manually edited, and assigned to the articles by Wikipedia editors.
- 7.
Other similarity measures are now under tests.
References
Bembenik R., Skonieczny Ł., Rybiński H., Niezgódka M. (eds.): Intelligent Tools for Building a Scientific Information Platform, Studies in Computational Intelligence, vol. 390, 2012, Springer, ISBN 978-3-642-24808-5, p. 277 doi:10.1007/978-3-642-24809-2
Koperwas J., Skonieczny Ł., Rybiński H., Struk W.: Development of a University Knowledge Base. In: Bembenik R. et al (eds.) Studies in Computational Intelligence. In: Intelligent Tools for Building a Scientific Information Platform: Advanced Architectures and Solutions, vol. 467, ISBN 978-3-642-35646-9, (2013), pp. 97–110, doi:10.1007/978-3-642-35647-6_8
Adamczyk T., Andruszkiewicz P.: Web Resource Retrieval System for Building a Scientific Information Database. (2013)
Andruszkiewicz, P., Gambin, T., Kryszkiewicz, M., Kozlowski, M., Lieber, K., Matusiak, A., Miedzinski, E., Morzy, M., Nachyla, B., Omelczuk, A., Rybinski, H., Skonieczny, L.: Synat/passim-report 4, b11 stage. Technical report (2012)
Zotero: http://www.zotero.org/
Ontology of Scientific Journal, Classification of Scientific Journals, http://www.science-metrix.com/eng/tools.htm
Gabrilovich E., Markovitch S.: Overcoming the brittleness bottleneck using Wikipedia: Enhancing text categorization with encyclopedic knowledge. In: AAAI (2006)
Gabrilovich E., Markovitch S., Wikipedia-based semantic interpretation for natural language processing. J. Artif. Intell. Res. 34, 443–498 (2009)
Medelyan O., Milne D., Legg C., Witten I.H.: Mining meaning from Wikipedia. Int. J. Hum. Comput. Stud. 67(9), 716–754 (2009)
Milne D., Medelyan O., Witten I.H.: Mining domain-specific thesauri from Wikipedia: a case study. In: Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence, Hong Kong, China, 2006, pp. 442–448
Milne D., Witten I.H.: An effective, low-cost measure of semantic relatedness obtained from Wikipedia links. In: Wikipedia and Artificial Intelligence: An Evolving Synergy, Chicago, IL, 2008, pp. 25–30
Medelyan O.: Human-competitive automatic topic indexing. Ph.D thesis, University of Waikato, Hamilton (2009)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Koperwas, J., Skonieczny, Ł., Kozłowski, M., Rybiński, H., Struk, W. (2014). University Knowledge Base: Two Years of Experience. In: Bembenik, R., Skonieczny, Ł., Rybiński, H., Kryszkiewicz, M., Niezgódka, M. (eds) Intelligent Tools for Building a Scientific Information Platform: From Research to Implementation. Studies in Computational Intelligence, vol 541. Springer, Cham. https://doi.org/10.1007/978-3-319-04714-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-04714-0_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04713-3
Online ISBN: 978-3-319-04714-0
eBook Packages: EngineeringEngineering (R0)